World: r3wp

You would have some memory overhead if you go the COPY route because 
of what Steeve said, but that may be dwarfed by the disk overhead 
savings.

correct.

its the speed of the read which will be the most  impact.

because each time you do a copy/part you create new buffers in memory 
which are not erased by the recycler so that you should consider

using always the same buffer especially if you do thousands and thousands 
access in one second

I would still have to use copy/part on the buffer if I went with 
Steeves idea.

You would get better performance improvements by figuring out how 
to queue your reads so you get better disk locality, which would 
lead to better internal buffer usage.

But you don't get it Steeve, I would still be using copy/part on 
the buffer filled by your read-io to get just the 16 bytes I want.

memory overhead is the point

performance is the point.

Not in this case, Steeve.

I don't think steeve gets that I don't need more than 16 bytes

performance you will have too with a well sized buff

let me put it another way Steeve, I will not be reading more than 
16 bytes per request (because I don't need any more than that) and 
it isn't a 16  bytes segment that is next to another 16 byte segment 
really I'm moving back and forth all over the file to get 16 byte 
segments each time.

Thats for this particular portion of what I'm doing.

The read-io is optimal in my other needs.

Steeve, he is doing random access. Unless he figures out how to queue 
his accesses, it won't matter if he uses the internal buffering or 
his own. The only way he could improve performance is through queueing.

Paul, there are other ways to reduce memory overhead that will get 
you more benefit, like using INSERT/part.

in what way?

can't read with insert/part

Not here. I was just using an example.

ok

I can't think of a better options than copy/part at this point

Without read queueing, neither can I.

what about pick?

be nice  to have pick/part

without the  overhead of copy

pick already works on /seek ports

Do you need to open/direct with read-io?

no

but the head moves as you read with /direct

must like forall does

It is not COPY that is buffering internally, it is OPEN without /direct.

I might do a test to see how fast 4 successive picks would be

and 16 picks

/seek is not buffered

it is like /direct

difference is that the index stays at head as you reference it.

How often do you need to do these reads, and can they be sorted in 
batches?

They do get sorted but they are done often and the batch sort is 
random sized depending on the request

You are using variable-length records rather than fixed length?

yes ;-)

Your wondering how right?

That is a lot slower. I am not wondering how, I've followed the discussions 
in your group.

slower than what?

Fixed length. Databases usually work in increments of disk pages 
because it is faster.

But at a cost

What if declared a field varchar[2000] and you only populate it with 
50?

Varchars are slower in practice. You can minimize the overhead of 
disk page access by packing pages if you have to. The OS reads in 
pages anyways.

I have minimized it to a greater extent.

A read of less than 1 disk page is just as slow as a read of 1 disk 
page.